ReasonFlux-Qwen3-dpo-GGUF

ReasonFlux-Qwen3-dpo is a fine-tuned version of Qwen3-1.7B, specially trained on the Gen-Verse/ReasonFlux-V2-Reasoner-DPO dataset to internalize template-augmented reasoning and structured thought processes via hierarchical reinforcement learning and direct preference optimization (DPO). This model excels in scientific and mathematical domains by producing transparent, step-by-step reasoning, symbolic derivations, detailed proofs, and robust code understanding across multiple languages, while also supporting structured outputs in formats like LaTeX, Markdown, JSON, CSV, and YAML for technical workflows. Designed for efficient deployment on mid-range GPUs, research clusters, and edge environments, ReasonFlux-Qwen3-dpo enhances coherence and adaptiveness, making it an ideal tool for advanced STEM reasoning and technical research applications.

Model Files

File Name	Quant Type	File Size
ReasonFlux-Qwen3-dpo.BF16.gguf	BF16	3.45 GB
ReasonFlux-Qwen3-dpo.F16.gguf	F16	3.45 GB
ReasonFlux-Qwen3-dpo.F32.gguf	F32	6.89 GB
ReasonFlux-Qwen3-dpo.Q2_K.gguf	Q2_K	778 MB
ReasonFlux-Qwen3-dpo.Q3_K_L.gguf	Q3_K_L	1 GB
ReasonFlux-Qwen3-dpo.Q3_K_M.gguf	Q3_K_M	940 MB
ReasonFlux-Qwen3-dpo.Q3_K_S.gguf	Q3_K_S	867 MB
ReasonFlux-Qwen3-dpo.Q4_0.gguf	Q4_0	1.05 GB
ReasonFlux-Qwen3-dpo.Q4_1.gguf	Q4_1	1.14 GB
ReasonFlux-Qwen3-dpo.Q4_K.gguf	Q4_K	1.11 GB
ReasonFlux-Qwen3-dpo.Q4_K_M.gguf	Q4_K_M	1.11 GB
ReasonFlux-Qwen3-dpo.Q4_K_S.gguf	Q4_K_S	1.06 GB
ReasonFlux-Qwen3-dpo.Q5_0.gguf	Q5_0	1.23 GB
ReasonFlux-Qwen3-dpo.Q5_1.gguf	Q5_1	1.32 GB
ReasonFlux-Qwen3-dpo.Q5_K.gguf	Q5_K	1.26 GB
ReasonFlux-Qwen3-dpo.Q5_K_M.gguf	Q5_K_M	1.26 GB
ReasonFlux-Qwen3-dpo.Q5_K_S.gguf	Q5_K_S	1.23 GB
ReasonFlux-Qwen3-dpo.Q6_K.gguf	Q6_K	1.42 GB
ReasonFlux-Qwen3-dpo.Q8_0.gguf	Q8_0	1.83 GB

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):